© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14978
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.87
    出版年
    -0.84
    GEBURTSDATUM
    -0.82
    Personensuche
    -0.81
     étoit
    -0.77
    Portály
    -0.77
     ComVisible
    -0.77
    OGND
    -0.75
     ModelExpression
    -0.75
     jsPsych
    -0.75
    POSITIVE LOGITS
     thought
    0.53
    <bos>
    0.52
    liferay
    0.52
    ClientSize
    0.46
    -
    0.46
     experienced
    0.43
     to
    0.43
    Jer
    0.42
    引き
    0.42
     often
    0.42
    Activations Density 0.017%

    No Known Activations